基于BP神经网络的自适应偏置比例导引

doi:10.12382/bgxb.2021.0594

摘要/Abstract

摘要： 针对传统的解析偏置比例导引在大范围机动时制导精度较差的缺陷，提出一种基于反向传播(BP)神经网络的自适应偏置比例导引律，通过BP神经网络在线精确求解偏置项。深入分析解析形式的求解偏置项的误差情况，论证不同参数对偏置项求解误差的影响。证明了参数与偏置项间存在的一一映射关系，采用BP神经网络对该映射进行高精度的拟合逼近。对多维输入参数进行灵敏度分析，以此为依据，为BP神经网络在参数空间批量化生成均衡样本。建立基于BP神经网络的偏置项求解模型，采用Adam学习方法对网络进行训练，并从理论上证明了制导律的稳定性。随后对训练效果进行测试，并对所提出的方法进行数学仿真验证。仿真结果表明：所提方法能在有限计算代价下有效提升制导精度，在不考虑弹体动力学情况下，终端角度误差均值仅为0.024°，可为工程应用提供参考。

关键词: 偏置比例导引, 映射关系, 灵敏度分析, BP神经网络

Abstract: To address the drawback of traditional analytical biased proportional guidance with poor guidance accuracy when maneuvering in a wide range，an adaptive biased proportional guidance law based on BP(Back propagation) neural network is proposed. The bias term is accurately solved online through the BP neural network. Firstly，the error of solving bias term in analytic form is investigated. Specifically，the influence of different parameters on the solution error of bias term is demonstrated. Secondly，the mapping relationship between parameter and constant term is proved. BP neural network is used to fit the mapping accurately. Thirdly，sensitivity analysis was performed for multidimensional input parameters，on this basis，equilibrium samples for BP neural network in parameter space batch are generated. Finally，the bias term solution model based on BP neural network is established and Adam learning method is used to train the network. In addition，the stability of the guidance law is proved in theory. The effectiveness of the training is tested and verified by mathematical simulation. The simulation results show that the proposed method can be implemented with limited computational cost and effectively improve guidance accuracy，and the average impact angle error is 0.024°. This paper provides a reference for engineering application.

Key words: biasedproportionalnavigationguidancelaw, mapping, sensitivityanalysis, backpropagationneuralnetwork

中图分类号:

TJ765.3

刘畅，王江，范世鹏，李伶，林德福. 基于BP神经网络的自适应偏置比例导引[J]. 兵工学报, 2022, 43(11): 2798-2809.

LIU Chang, WANG Jiang, FAN Shipeng, LI Ling, LIN Defu. BP Neural Network-Based Adaptive Biased Proportional Navigation Guidance Law[J]. Acta Armamentarii, 2022, 43(11): 2798-2809.

参考文献

［1］姚郁，郑天宇，贺风华，等.飞行器末制导中的几个热点问题与挑战［J］.航空学报，2015，36(8): 2696-2716.
YAO Y, ZHENG T Y, HE F H, et al. Several hot issues and challenges in terminal guidance of flight vehicles［J］. Acta Aeronautica et Astronautica Sinica, 2015, 36(8): 2696-2716. (in Chinese)
［2］ ZHANG Y A, MA G X, LIU A L. Guidance law with impact time and impact angle constraints［J］. Chinese Journal of Aeronautics, 2013, 26(4): 960-966.
［3］ LIU D, QI Z K. Impact angle and final position constrained optimal guidance law［J］. Transactions of Beijing Institute of Technology, 2001, 21(3): 278-281.
［4］ YUAN P J, CHERN J S. Ideal proportional navigation［J］. Journal of Guidance, Control, and Dynamics, 1992, 15(5): 1161-1165.
［5］ ERER K S，KERMAL OZGOREN M. Control of impact angle using biased proportional navigation［C］∥Proceedings of AIAA Guidance, Navigation, and Control (GNC) Conference. Boston, US: AIAA, 2013: AIAA2013-5113.
［6］ KIM B S，LEE J G，HAN H S. Biased PNG law for impact with angular constraint［J］. IEEE Transactions on Aerospace and Electronic Systems, 1998, 34(1): 277-288.
［7］ LEE C H，KIM T H，TAHK M J. Interception angle control guidance using proportional navigation with error feedback［J］.Journal of Guidance，Control，and Dynamics， 2013, 36(5): 1556-1561.
［8］ GAO F, TANG S, SHI J, et al. A bias proportional navigation guidance law based on terminal impact angle constraint［J］. Transactions of Beijing Institute of Technology, 2014, 34(3): 277-282.
［9］马帅，王旭刚，王中原，等.带初始前置角和末端攻击角约束的偏置比例导引律设计以及剩余飞行时间估计［J］.兵工学报，2019，40(1):68-78.
MA S，WANG X G，WANG Z Y，et al. BPNG law with arbitrary initial lead angel and terminal impact angle constraint and time-to-go estimation［J］. Acta Armamentarii, 201 9, 40(1): 68-78. (in Chinese)
［10］王广帅，林德福，范世鹏，等.一种适用于红外制导弹药的偏置比例导引律［J］.系统工程与电子技术，2016，38(10): 2346-2352.
WANG G S，LIN D F，FAN S P，et al. Biased proportional navigation applicable for infrared guidance munitions［J］. Systems Engineering and Electronics, 2016, 38(10): 2346-2352.(in Chinese)
［11］ LEE C H，KIM T H，TAHK M J. Biased PNG for target observability enhancement against nonmaneuvering targets［J］. IEEE Transactions on Aerospace & Electronic Systems, 2015, 51(1): 2-17.
［12］ ERER K S，MERTTOPCUOGLU O. Indirect control of impact angle against stationary targets using biased PPN［C］∥Proceedings of AIAA Guidance，Navigation，and Control Conference. Toronto: AIAA，2010: AIAA 2010-8184.
［13］ HONG D，KIM M，PARK S. Study on Reinforcement Learning-Based Missile Guidance Law［J］.Applied Sciences，2020，10(18): 6567.
［14］田春军.基于BP神经网络的潜地导弹落点参数计算方法［J］.兵器装备工程学报，2021，42(4): 145-149.
TIAN C J. Calculation method of impact point parameter based on BP neural network for submarine launched ballistic missile［J］. Journal of Ordnance Equipment Engineering，2021，42(4): 145-149. (in Chinese)
［15］ SHAO G H J，XU Z，WANG X M，et al. Adaptive three-dimensional guidance law based on neural dynamic surface control［C］∥Proceedings of 2016 IEEE International Conference on Aircraft Utility Systems (AUS). Beijing，China: IEEE，2016: 92-97.
［16］王因翰，范世鹏，吴广，等.基于GRU的敌方拦截弹制导律快速辨识方法［J］. 航空学报, 2022, 43(2): 398-409.
WANG Y H，FAN S P，WU G，et al. Fast guidance law identification approach for incoming missile based on GRU network［J］. Acta Aeronautica et Astronautica Sinica, 2022, 43(2): 398-409. (in Chinese)
［17］ FILICI C，SNCHEZ PEA R S. Online guidance updates using neural networks［J］.Acta Astronautica，2010，66(3/4): 477-485.
［18］余跃，王宏伦.基于深度学习的高超声速飞行器再入预测校正容错制导［J］.兵工学报，2020，41(4): 656-669.
YU Y，WANG H L. Deep learning-based reentry predictor-corrector fault-tolerant guidance for Hypersonic vehicles［J］. Acta Armamentarii，2020，41(4): 656-669. (in Chinese)
［19］张宏鹏，黄长强，轩永波，等.基于深度神经网络的无人作战飞机自主空战机动决策［J］.兵工学报，2020，41(8): 1613-162.
ZHANG H P，HUANG C Q，XUAN Y B，et al. Maneuver decision of autonomous air combat of unmanned combat aerial vehicle based on deep neural network［J］. Acta Armamentarii，2020，41(8): 1613-162. (in Chinese)
［20］ GUO Y H，LI X，ZHANG H J，et al. Data-driven method for impact time control based on proportional navigation guidance［J］.Journal of Guidance，Control，and Dynamics，2020，43(5): 955-966.
［21］ COTTRELL R G，VINCENT T L，SADATI S H. Minimizing interceptor size using neural networks for terminal guidance law synthesis［J］. Journal of Guidance，Control，and Dynamics，1996，19(3):557-562.
［22］ NARENDRA K S, PARTHASARATHY K. Identification and control of dynamical systems using neural networks［J］. IEEE Transactions on Neural Net Works，1990，1(1): 4-27.
［23］ FUNAHASHI K I. On the approximate realization of continuous mappings by neural networks［J］.Neural networks，1989，2(3): 183-192.
［24］ HECHT-NIELSEN R. Theory of the backpropagation neural network[C]∥Proceedings of the International 1989 Joint Conference on Neural Networks. Washington, DC, US: IEEE, 1989(1): 593-605.
［25］ WANG Y H，FAN S P，WANG J，et al. Quick identification of guidance law for an incoming missile using multiple-model mechanism［J］. Chinese Journal of Aeronautics，2022, 35(9): 282-292.
［26］ RAFAEL Y. Modern missile guidance［M］. Boca Raton: CRC Press，2007: 102-112.

[1]	魏伟, 张竞文, 常思江, 王浩圣, 王建中. 基于Sobol和EFAST法的枪弹转动角速度全局灵敏度仿真分析[J]. 兵工学报, 2022, 43(9): 2408-2416.
[2]	罗中峰，管小荣，徐诚. 面向弹丸炮口状态的自行火炮结构参数全局灵敏度[J]. 兵工学报, 2021, 42(2): 254-267.
[3]	陈鹏霏，和鹏，于泰龙，刘巧伶. 基于梯度搜索法的非线性结构可靠性分析方法[J]. 兵工学报, 2021, 42(1): 175-184.
[4]	林通，钱林方，付佳维，王明明. 火炮高平机参数辨识与灵敏度[J]. 兵工学报, 2020, 41(9): 1736-1744.
[5]	李阳天，李海滨，韦广梅，翁洁鑫. 基于改进型多项式混沌展开的固体火箭发动机药柱低温点火不确定性量化分析[J]. 兵工学报, 2020, 41(1): 40-48.
[6]	马帅，王旭刚，王中原，杨靖. 带初始前置角和末端攻击角约束的偏置比例导引律设计以及剩余飞行时间估计[J]. 兵工学报, 2019, 40(1): 68-78.
[7]	罗中峰，管小荣，徐亚栋，徐诚. 某火炮弹丸在炮口状态的动态灵敏度分析[J]. 兵工学报, 2017, 38(12): 2328-2336.
[8]	刘勤，孙志礼，钱云鹏，刘英. 基于概率功能度量的疲劳可靠寿命分析方法[J]. 兵工学报, 2016, 37(8): 1530-1535.
[9]	巩亚东，孙瑶，刘寅. 低速单向走丝电火花线切割钛合金TC4表面粗糙度试验研究与建模[J]. 兵工学报, 2016, 37(6): 1058-1065.
[10]	易怀军，刘宁，张相炎，丁传俊. 基于优化的非等间隔灰色理论和BP神经网络的身管磨损量预测[J]. 兵工学报, 2016, 37(12): 2220-2225.
[11]	鲜勇，李少朋，李邦杰. 基于BP神经网络的固体导弹耗尽关机姿态调制方法研究[J]. 兵工学报, 2015, 36(4): 668-673.
[12]	程广利，胡金华，张明敏. 浅海声场对不确定环境参数的灵敏度分析方法[J]. 兵工学报, 2014, 35(4): 567-571.
[13]	杨丽，孙志礼，印明昂，王宇宁. 基于多属性决策灵敏度分析的供弹机压弹机构优化设计[J]. 兵工学报, 2014, 35(2): 241-247.
[14]	唐玉娟，王新杰，王炅. 引信安全系统的直线超声电机设计与试验研究[J]. 兵工学报, 2014, 35(1): 27-34.
[15]	刘辉, 蔡仲昌, 曹华夏, 项昌乐. 车辆动力传动系统扭转强迫振动响应灵敏度研究[J]. 兵工学报, 2011, 32(8): 939-944.